Back to skill

Security audit

企业-产品竞争力与技术实力评估

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward new-product research prompt that uses web search to summarize public product information, with no code, persistence, credential access, or local system changes.

Install this if you want Chinese-language briefs on recent product launches using public web sources. Review the cited or named sources before making business, investment, or procurement decisions, and avoid including confidential strategy details in prompts because the workflow is designed to perform external searches.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger description is broad enough to overlap with many generic analysis and summarization requests, which can cause the skill to activate outside its intended scope. That increases the chance of unintended network access and externally sourced output being injected into unrelated user workflows without clear user intent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill instructs the agent to perform web searches across third-party sources and generate conclusions from them, but it does not clearly tell the user that external sources will be accessed. This creates a transparency and consent issue and raises the risk of users receiving unvetted external information or having their query context sent to third-party services unexpectedly.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

整个技能文档从名称字段到输出示例均默认并强制使用中文,没有说明是否支持其他语言,也未提供用户可选语言/locale 的机制。根据规则,未经用户选择而强制特定语言属于自然语言层面的组织策略风险。

Content

No source excerpt is available for this finding.